Anastasia A. Matveeva

Anastasia A. Matveeva

Auto-generated profile, based on publicly available information

Anastasia A. Matveeva

ITMO University

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 November 2022
Verified
Book Chapter
Closed access
PDF file
Pavel PosokhovPavel Posokhov
Pavel Posokhov
AMAnastasia Matveeva
Anastasia Matveeva
Olesia KoroteevaOlesia Koroteeva
Olesia Koroteeva
AMAnton Matveev
Anton Matveev
YMYuri N. Matveev
Yuri N. Matveev

1 February 2019 in Scientific and Technical Journal of Information Technologies, Mechanics and Optics
Verified
Journal Article
Open access
PDF file
AMAnastasia A. Matveeva
Anastasia A. Matveeva
IKIuliia Kim
Iuliia Kim
IVIlia Viksnin
Ilia Viksnin
The paper presents the study of multi-agent robotic systems in the context of information security providing. The preference is given to decentralized collective strategy of group management due to secure and consensual agent interaction by common communication channel. For the correct and effective functioning of the robotic group there is a necessity in providing security of information transfer via communication channels. We consider the mechanisms of “hard” and “soft” security in robotic systems. Special consideration is given to pragmatic information integrity maintenance. To avoid violation occurrence in this integrity category the method based on credit theory was developed. The method implies regulation of information volume transferred by agents through determination of fixed amount for information conventional units per time unit (installment plan). In case of data retention by an agent its payment value is reduced subsequently, thus, its indebtedness is increased. After installment plan period completion agent’s level of trust and reputation is calculated for each agent. When a new agent is incorporated into the group the credit is determined, at which the new agent will get not full information from the other group members but information reduced by the established interest rate. At the same time, this agent must transmit data in accordance with predetermined installment plan conditions. After credit period completion the decision is made whether the new agent is accepted or blocked. To assess the effectiveness of the proposed method the interaction in robotic group consisted of ten agents was modelled. Two new agents were introduced into the group, and one of them was a saboteur. The threshold value of indebtedness for the agent's acceptance to the group is the half of established credit size. Series of independent tests were carried out and the saboteur was blocked in the 90.8 % of them.

22 November 2024
Verified
Book Chapter
Closed access
PDF file
EVElizaveta Vologina
Elizaveta Vologina
AMAnastasiia Matveeva
Anastasiia Matveeva
Olesia KoroteevaOlesia Koroteeva
Olesia Koroteeva
YMYuri N. Matveev
Yuri N. Matveev
NBNursaule Burambayeva
Nursaule Burambayeva

1 September 2018 in Scientific and Technical Journal of Information Technologies, Mechanics and Optics
Verified
Journal Article
Open access
PDF file
IKIuliia Kim
Iuliia Kim
AMAnastasia A. Matveeva
Anastasia A. Matveeva
IVIlia Viksnin
Ilia Viksnin
We consider computer vision issues with a view to embed it into vehicles and automate the traffic process by detecting of objects and road users. Three basic stages of pattern recognition in the image are enumerated: image preparation for analysis, analysis, object classification. The search of methods that improve pattern recognition quality and provide visual information semantic integrity was carried out respectively for each stage. We propose to use normalization for the first stage, which allows making image objects insensitive to the light changes. For the second stage clustering method based on particle swarm optimization and k-means was developed that provides automatic tuning of clustering parameters. During the third stage Haar cascades with normalized training samples are proposed for application providing object unification and giving an opportunity to use less amount of training samples. Car images provided by Stanford University laboratory and publicly available were used for training and testing. To assess the effectiveness of the developed pattern recognition algorithm, 300 test images were blurred. We compared the results of the proposed algorithm operation with Haar cascades operating results without normalized training samples and without preparation for classification. Haar cascades with non-normalized training images provided correct car recognition in 8% of cases, meanwhile, the proposed algorithm recognized 72% of cases including those 8% of images. Visual information semantic integrity preservation is an important aspect in context of road traffic, because incorrect object detection can cause fatal consequences. The proposed algorithm of image analysis reduces the probability of error occurrences during pattern recognition.

1 August 2023 in Scientific and Technical Journal of Information Technologies, Mechanics and Optics
Verified
Journal Article
Open access
PDF file
AMA.A. Matveeva
A.A. Matveeva
Olesia KoroteevaOlesia Koroteeva
Olesia Koroteeva
Currently, various natural language processing tasks often require large data sets. However, for many tasks, collecting large datasets is quite tedious and expensive, and requires the involvement of experts. An increase in the amount of data can be achieved using methods of data augmentation, however, the use of classical approaches can lead to the inclusion of phrases in the data corpus that differ in the speech style and vocabulary of the target person, which can lead to both a change in the target class as well as the appearance of replicas with unnatural vocabulary use and lack of meaning. In this context, a new method for test data enrichment is proposed that takes into account the person’s style and vocabulary. In this article, a new method for expanding text data that preserves individual language features and vocabulary is proposed. The core of the method is to create individual templates for each person based on the analysis of syntactic trees of propositions and then to create new replicas according to the generated templates. The method was tested on the task of assessing the user’s emotional state in a dialogue. The search was carried out for data sets in English and Russian. The proposed method made it possible to improve the quality of solving these problems for both the English and Russian languages. Up to a 2 % increase in accuracy and weighted F1 metrics has been noted for various models. The results of the work can be applied to improve the accuracy and weighted F1 metrics of models designed to solve various problems for the English and Russian languages.